© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236140
    Prev
    Next
    INDEX
    Explanations

    electrical components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ওসি
    0.47
    邮箱
    0.43
    Eta
    0.40
    थ
    0.40
    包人
    0.38
     Martha
    0.37
    ಟಕ
    0.36
    Oil
    0.35
    血液
    0.35
     মাথ
    0.35
    POSITIVE LOGITS
    grim
    0.43
    樑
    0.40
    Hughes
    0.40
     Joko
    0.40
     शमी
    0.39
     Plugging
    0.38
     crown
    0.37
    sockets
    0.37
     !}
    0.37
    neux
    0.37
    Activations Density 0.000%

    No Known Activations